The Semantic Infrastructure Opportunity: Building Meaningful Operational Frameworks

2026-01-05 · Source: Modern Data 101 · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Data Science & Analytics · Depth: Advanced, long

Summary

Jessica Talisman, a Semantic Engineer and founder of The Ontology Pipeline, highlights how semantic infrastructure, particularly entity resolution, provides tangible value for ontologists and semantic engineers. She explains that while traditional semantic work often remains siloed, entity resolution makes it measurably operational by improving match rates and reducing false positives. The article introduces tools like Senzing's sz-semantics library and the Senzing thesaurus, which operationalize the Ontology Pipeline framework. This framework systematically builds semantic knowledge management systems from controlled vocabularies to knowledge graphs, enabling semantic interpretation for entity resolution. The author emphasizes that human expertise is crucial for curating entity definitions and ensuring semantic quality, as demonstrated by projects like Strwythura and the National Information Exchange Model (NIEM) case study.

Key takeaway

For AI Architects and Data Engineers building robust knowledge infrastructures, integrating the Ontology Pipeline with entity resolution tools like Senzing's sz-semantics is crucial. This approach transforms raw data matches into semantically rich, queryable knowledge graphs, directly demonstrating the ROI of semantic engineering. You should prioritize structuring your domain thesaurus in SKOS and planning for its extension to ensure high-fidelity disambiguation and contextual understanding for AI applications.

Key insights

Semantic infrastructure, especially entity resolution, makes ontology work measurably operational and critical for AI systems.

Principles

• Semantic systems require progressive context-building.
• Entity resolution needs semantic interpretation to add meaning.
• Human-in-the-loop curation is essential for semantic quality.

Method

The Ontology Pipeline framework progresses from controlled vocabularies to taxonomies, thesauri, ontologies, and knowledge graphs, each stage building semantic maturity.

In practice

• Audit existing semantic assets for quality and SKOS compliance.
• Migrate taxonomies to SKOS format for broader interoperability.
• Engage with open-source tools like sz-semantics and Strwythura.

Topics

• Ontology Pipeline Framework
• Entity Resolution
• Semantic Engineering
• Knowledge Graphs
• SKOS Thesauri

Code references

• senzing-garage/sz-semantics
• DerwenAI/strwythura

Best for: AI Architect, Data Engineer, MLOps Engineer

Related on AIssential

• The Semantic Infrastructure Opportunity — Semantic infrastructure, especially thesauri, transforms raw entity resolution matches into meaningful, contextualized knowledge.
• A Practitioner’s Guide to Taxonomies, Part III — SKOS formalizes taxonomies with URIs and rich properties, making them machine-readable and essential for AI systems.
• What Makes Knowledge Graphs AI-Ready — Knowledge Graphs for AI bridge siloed data semantics with organizational ontology for machine-readable reasoning.
• The Ontology Pipeline™, Refresh — Effective semantic knowledge infrastructure requires a structured pipeline, human expertise, and robust governance, not just AI-generated outputs.
• Building an Ontology-Driven Supply Chain Intelligence Platform on Snowflake — Ontology-driven semantic models on Snowflake unify supply chain data for consistent reasoning and AI-powered intelligence.
• Google Just Entered the Semantic War. And It Brought a Different Weapon. — The core battle in enterprise AI is defining data meaning, not just model performance.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Modern Data 101.